© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3215
    Prev
    Next
    INDEX
    Explanations

    writing text of a specific word count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pretentious
    1.67
     Cocktail
    1.62
     Eindruck
    1.61
     đoạn
    1.59
     nhỉ
    1.58
    weird
    1.55
    蔫
    1.55
     Cough
    1.54
     बदमाश
    1.53
     Drummond
    1.53
    POSITIVE LOGITS
    น
    1.23
    ares
    1.20
    arel
    1.16
    ORS
    1.16
    Applied
    1.16
     ympä
    1.15
    ses
    1.12
    öp
    1.11
    т
    1.11
    عام
    1.11
    Activations Density 1.014%

    No Known Activations